An Exploration of Large Language Models for Verification of News Headlines

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study explores the capabilities of ChatGPT in news headline verification across different prompts and languages. We introduce an optimal prompt design and a novel difficulty ratio metric to analyze ChatGPT's performance across various statement resources. Our findings highlight ChatGPT's promising accuracy and cross-linguistic adaptability in fact-checking, while also identifying areas for further investigation, especially in expanding the analysis beyond headlines and exploring other Large Language Models (LLMs). Our findings suggest it is highly promising to leverage an LLM such as ChatGPT as a general tool in combating misinformation, enhancing the trustworthiness of digital information, and increasing trust-worithiness of text data mining algorithms by providing more reliable data sources for the algorithms.

Original languageEnglish (US)
Title of host publicationProceedings - 23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
EditorsJihe Wang, Yi He, Thang N. Dinh, Christan Grant, Meikang Qiu, Witold Pedrycz
PublisherIEEE Computer Society
Pages197-206
Number of pages10
ISBN (Electronic)9798350381641
DOIs
StatePublished - 2023
Externally publishedYes
Event23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023 - Shanghai, China
Duration: Dec 1 2023Dec 4 2023

Publication series

NameIEEE International Conference on Data Mining Workshops, ICDMW
ISSN (Print)2375-9232
ISSN (Electronic)2375-9259

Conference

Conference23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
Country/TerritoryChina
CityShanghai
Period12/1/2312/4/23

Keywords

  • Information trust
  • large language models
  • misinformation
  • prompting

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'An Exploration of Large Language Models for Verification of News Headlines'. Together they form a unique fingerprint.

Cite this